| commit | 652cb7975418a2f6a5479946187b818013d15049 | [log] [tgz] |
|---|---|---|
| author | Scott Todd <scott.todd0@gmail.com> | Wed May 01 15:54:58 2024 -0700 |
| committer | GitHub <noreply@github.com> | Wed May 01 15:54:58 2024 -0700 |
| tree | af5cd84e14d48574b09a045b798dbee48a6f89f7 | |
| parent | e6d8aa70904f182881f388137708c07e5127483e [diff] |
Convert (semi) recent tutorial gists into blog posts. (#17261) Better late than never? I've found a few people asking for information that these pages provide, so hosting them up on the website seems nice vs just linking to the gists. | Title | Original gist | Website preview | | -- | -- | -- | Exploring IREE CPU microkernels on a simple matmul example | [gist link](https://gist.github.com/bjacob/2c160c102cee33562826c730945b49f2) | https://scotttodd.github.io/iree/community/blog/2024-01-22-exploring-cpu-microkernels-on-a-matmul-example/ IREE/MLIR/Linalg tutorial | [gist link](https://gist.github.com/bjacob/2e662b3d2259d99aec15a43bf0e7b325) | https://scotttodd.github.io/iree/community/blog/2024-01-29-iree-mlir-linalg-tutorial/ MLIR syntax highlighting will still need some work to enable on the website, but otherwise I think these look good when rendered through mkdocs. Note that since the previous latest blog posts on https://iree.dev/community/blog/ are from 2021, that page is not very discoverable (we kept it around but more hidden). If we start using it more we could add it to the top level website nav.
IREE (Intermediate Representation Execution Environment, pronounced as “eerie”) is an MLIR-based end-to-end compiler and runtime that lowers Machine Learning (ML) models to a unified IR that scales up to meet the needs of the datacenter and down to satisfy the constraints and special considerations of mobile and edge deployments.
See our website for project details, user guides, and instructions on building from source.
IREE is still in its early phase. We have settled down on the overarching infrastructure and are actively improving various software components as well as project logistics. It is still quite far from ready for everyday use and is made available without any support at the moment. With that said, we welcome any kind of feedback on any communication channels!
See our website for more information.
IREE is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.